Evaluation of polymer electrolyte membrane electrolysis by explainable machine learning, optimum classification model, and active learning

Basit Öğe Kaydı
dc.authoridGunay, M. Erdem/0000-0003-1282-718X
dc.contributor.authorGunay, M. Erdem
dc.contributor.authorTapan, N. Alper
dc.date.accessioned2024-07-18T20:40:40Z
dc.date.available2024-07-18T20:40:40Z
dc.date.issued2023
dc.departmentİstanbul Bilgi Üniversitesien_US
dc.description.abstractIn this work, a database of 789 experimental points extracted from 30 academic publications was used. The primary objective was to use novel machine-learning techniques to investigate how descriptor variables affect current density, power density, and polarization, and to identify rules or pathways that result in high current density, low power density, and low polarization. First, Shapley analysis was done to find and compare the magnitude of the contribution of each variable on current density as well as the positive and negative effects of all the variables. Then, correlation coefficient heat maps were provided to display the existence of any linear relationship between the input and output variables. Additionally, k-nearest neighbor classification (as an optimal model) was able to demonstrate the entire impact of all features on the outputs. Finally, the Bayesian optimization algorithm showed that the optimum performance of polymer electrolyte membrane electrolyzer could be reached with less experimental effort and time than the usual research plan. It was then concluded that machine learning methods can aid in determining the best conditions for designing a polymer electrolyte membrane electrolyzer to produce hydrogen, which can be used to guide the planning of future experiments. [GRAPHICS] .en_US
dc.identifier.doi10.1007/s10800-022-01786-8
dc.identifier.endpage433en_US
dc.identifier.issn0021-891X
dc.identifier.issn1572-8838
dc.identifier.issue3en_US
dc.identifier.scopus2-s2.0-85142497297en_US
dc.identifier.scopusqualityQ2en_US
dc.identifier.startpage415en_US
dc.identifier.urihttps://doi.org/10.1007/s10800-022-01786-8
dc.identifier.urihttps://hdl.handle.net/11411/7173
dc.identifier.volume53en_US
dc.identifier.wosWOS:000887875600003en_US
dc.identifier.wosqualityQ3en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherSpringeren_US
dc.relation.ispartofJournal of Applied Electrochemistryen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectShapley Analysisen_US
dc.subjectElectrolyzeren_US
dc.subjectData Miningen_US
dc.subjectHydrogen Productionen_US
dc.subjectK-Nearest Neighbor Algorithmen_US
dc.subjectPolymer Electrolyte Membraneen_US
dc.subjectPem Water Electrolyzeren_US
dc.subjectPorous Transport Layeren_US
dc.subjectSelective Co Oxidationen_US
dc.subjectNoble-Metal Catalystsen_US
dc.subjectHydrogen Evolutionen_US
dc.subjectKnowledge Extractionen_US
dc.subjectOperating Parametersen_US
dc.subjectStatistical-Analysisen_US
dc.subjectIonomer Contenten_US
dc.subjectPerformanceen_US
dc.titleEvaluation of polymer electrolyte membrane electrolysis by explainable machine learning, optimum classification model, and active learningen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

Web of Science Indexed Publications
Scopus Indexed Publications